ramdhanfirdaus commited on
Commit
f052bbf
1 Parent(s): b99ef4a

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33586be5fbd82fae9ac6620008892678b5f2d7dd7e5a8ef6a3da78d07653c26b
3
  size 50349441
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6320c9079aabaf1f64db10d1ae49aad02d1db46f6862ed4cb4883ac3068691df
3
  size 50349441
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12cd486f70d22320e3dea3f1a140dee210d82739ecaf04b0b58ec946113e98af
3
  size 100691721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd6b31aaca586a4db71a6f7b9732a1d1c650bc4427ddf84a3506ae8d8170c14
3
  size 100691721
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d9a5e96d5319f578e3676c8a6aaa1d019c2f577ff8abb55dcf5d74b47d9273c
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b844b6d05ca4a0d574e8b563577b5a55af86779b464ff872bc6a0d1764aa57d5
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4694663286209106,
3
- "best_model_checkpoint": "./outputs/checkpoint-1900",
4
- "epoch": 1.384335154826958,
5
  "eval_steps": 100,
6
- "global_step": 1900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -273,13 +273,27 @@
273
  "eval_samples_per_second": 21.226,
274
  "eval_steps_per_second": 2.656,
275
  "step": 1900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
276
  }
277
  ],
278
  "logging_steps": 100,
279
  "max_steps": 4116,
280
  "num_train_epochs": 3,
281
  "save_steps": 100,
282
- "total_flos": 1.1327940508889088e+17,
283
  "trial_name": null,
284
  "trial_params": null
285
  }
 
1
  {
2
+ "best_metric": 1.4534634351730347,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2000",
4
+ "epoch": 1.4571948998178508,
5
  "eval_steps": 100,
6
+ "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
273
  "eval_samples_per_second": 21.226,
274
  "eval_steps_per_second": 2.656,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.46,
279
+ "learning_rate": 0.0002,
280
+ "loss": 1.4481,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 1.46,
285
+ "eval_loss": 1.4534634351730347,
286
+ "eval_runtime": 296.7451,
287
+ "eval_samples_per_second": 21.143,
288
+ "eval_steps_per_second": 2.645,
289
+ "step": 2000
290
  }
291
  ],
292
  "logging_steps": 100,
293
  "max_steps": 4116,
294
  "num_train_epochs": 3,
295
  "save_steps": 100,
296
+ "total_flos": 1.192408030183342e+17,
297
  "trial_name": null,
298
  "trial_params": null
299
  }